Unsupervised Feature Learning for RGB-D Image Classification

By I-Hong Jhuo, Shenghua Gao, Liansheng Zhuang, D. T. Lee, Yi Ma. 2014

25 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Ling Shao
2. Jianfei Cai
3. G. Wang
4. Li Liu
5. Jiwen Lu
6. Dacheng Tao
7. Jungong Han
8. Tat-Jen Cham

In Media Technology

1. Ling Shao
2. Tat-Jen Cham
3. Jianfei Cai
4. Jiwen Lu
5. Jungong Han
6. G. Wang
7. Li Liu

In Signal Processing

1. Ling Shao
2. Tat-Jen Cham
3. Jianfei Cai
4. Jiwen Lu
5. Jungong Han
6. G. Wang
7. Ziyun Cai
8. Li Liu

Citations in the corpus

• RGB-D datasets using microsoft kinect or similar sensors: a survey (2016, background): “Therefore, the scene recognition rates are relatively low, which are 75.9 ± 2.9 (RGB), 65.8 ± 2.7 (Depth) and 76.2 ± 3.2 (RGB-D) reported in [42].”
• Large-Margin Multi-Modal Deep Learning for RGB-D Object Recognition (2015, methodology): “In addition, with their constraint, [23] requires the learned features for different modalities to be the same in dimensions while our method could capture more general and diverse information.”